Skip to content
K = 0.731

RockMatrix Releases Open-Weight EdgeRock-4B With Fixed-Size Attention KV Cache

1 reports 1 reporting sources 3 hours agoNew

Understand the event

AI overview

RockMatrix, together with HKUST, CMU, and other universities, released EdgeRock-4B for text and image reasoning, making its model weights and inference code publicly available for commercial use. Adapted from Qwen3.5-4B, the model uses a mechanism called Rock Memory Anchors to keep its attention KV cache at 72 MiB—a reported 99.1% reduction at a 256K context length. In reported tests using 32K input tokens and 32K output tokens on a single Hopper GPU with 80GB of memory, EdgeRock-4B reached 12,124 tokens per second across 512 concurrent sequences, or 6.42 times the source model’s throughput. The report also said it retained 96.3% of the source model’s average pass rate on AIME 2024–2026.

Generated by AI from reports · Updated 24 minutes ago

Latest development10/26 14:45 (UTC+8)
RockMatrix and University Partners Release EdgeRock-4B With Fixed-Size KV Cache量子位

Read next

More changes in today’s briefingNvidia open-sources Flora with projected robot video labeling costs up to 125x lower than GPT-6 Astra

Report timeline

Follow the reports to explore different sides of the event.

10/26
  1. 量子位
    RockMatrix and University Partners Release EdgeRock-4B With Fixed-Size KV Cache

    RockMatrix, together with HKUST, CMU, and other universities, released EdgeRock-4B with open model weights and inference code for text and image reasoning. Adapted from Qwen3.5-4B, its Rock Memory Anchors mechanism keeps attention KV Cache at 72 MiB, a reported 99.1% reduction at 256K context. In reported tests with 32K input and 32K output on one Hopper 80GB GPU, it delivered 12124 tokens/s at 512 concurrent sequences, 6.42 times the source model’s throughput, while retaining 96.3% of its average AIME 2024–2026 pass rate.

Keep up with AI, one email a day

Model releases, price changes and compute developments, with original sources. Free, confirmed by email, and easy to unsubscribe. Read a past issue

Event heat trend

There is not enough continuous observation data to plot a trend yet.